Merge branch 'pnfs-submit' of git://git.open-osd.org/linux-open-osd

* 'pnfs-submit' of git://git.open-osd.org/linux-open-osd: (32 commits)
  pnfs-obj: pg_test check for max_io_size
  NFSv4.1: define nfs_generic_pg_test
  NFSv4.1: use pnfs_generic_pg_test directly by layout driver
  NFSv4.1: change pg_test return type to bool
  NFSv4.1: unify pnfs_pageio_init functions
  pnfs-obj: objlayout_encode_layoutcommit implementation
  pnfs: encode_layoutcommit
  pnfs-obj: report errors and .encode_layoutreturn Implementation.
  pnfs: encode_layoutreturn
  pnfs: layoutret_on_setattr
  pnfs: layoutreturn
  pnfs-obj: osd raid engine read/write implementation
  pnfs: support for non-rpc layout drivers
  pnfs-obj: define per-inode private structure
  pnfs: alloc and free layout_hdr layoutdriver methods
  pnfs-obj: objio_osd device information retrieval and caching
  pnfs-obj: decode layout, alloc/free lseg
  pnfs-obj: pnfs_osd XDR client implementation
  pnfs-obj: pnfs_osd XDR definitions
  pnfs-obj: objlayoutdriver module skeleton
  ...

26 files changed, 3516 insertions, 278 deletions

diff --git a/fs/nfs/Kconfig b/fs/nfs/Kconfig
index ba306658a6d..81515545ba7 100644
--- a/fs/nfs/Kconfig
+++ b/fs/nfs/Kconfig
@@ -87,6 +87,16 @@ config NFS_V4_1
 config PNFS_FILE_LAYOUT
 	tristate
 
+config PNFS_OBJLAYOUT
+	tristate "Provide support for the pNFS Objects Layout Driver for NFSv4.1 pNFS (EXPERIMENTAL)"
+	depends on NFS_FS && NFS_V4_1 && SCSI_OSD_ULD
+	help
+	  Say M here if you want your pNFS client to support the Objects Layout Driver.
+	  Requires the SCSI osd initiator library (SCSI_OSD_INITIATOR) and
+	  upper level driver (SCSI_OSD_ULD).
+
+	  If unsure, say N.
+
 config ROOT_NFS
 	bool "Root file system on NFS"
 	depends on NFS_FS=y && IP_PNP
diff --git a/fs/nfs/Makefile b/fs/nfs/Makefile
index 4776ff9e381..6a34f7dd0e6 100644
--- a/fs/nfs/Makefile
+++ b/fs/nfs/Makefile
@@ -15,9 +15,11 @@ nfs-$(CONFIG_NFS_V4)	+= nfs4proc.o nfs4xdr.o nfs4state.o nfs4renewd.o \
 			   delegation.o idmap.o \
 			   callback.o callback_xdr.o callback_proc.o \
 			   nfs4namespace.o
-nfs-$(CONFIG_NFS_V4_1)	+= pnfs.o
+nfs-$(CONFIG_NFS_V4_1)	+= pnfs.o pnfs_dev.o
 nfs-$(CONFIG_SYSCTL) += sysctl.o
 nfs-$(CONFIG_NFS_FSCACHE) += fscache.o fscache-index.o
 
 obj-$(CONFIG_PNFS_FILE_LAYOUT) += nfs_layout_nfsv41_files.o
 nfs_layout_nfsv41_files-y := nfs4filelayout.o nfs4filelayoutdev.o
+
+obj-$(CONFIG_PNFS_OBJLAYOUT) += objlayout/
diff --git a/fs/nfs/callback.h b/fs/nfs/callback.h
index 46d93ce7311..b257383bb56 100644
--- a/fs/nfs/callback.h
+++ b/fs/nfs/callback.h
@@ -167,6 +167,23 @@ extern unsigned nfs4_callback_layoutrecall(
 
 extern void nfs4_check_drain_bc_complete(struct nfs4_session *ses);
 extern void nfs4_cb_take_slot(struct nfs_client *clp);
+
+struct cb_devicenotifyitem {
+	uint32_t		cbd_notify_type;
+	uint32_t		cbd_layout_type;
+	struct nfs4_deviceid	cbd_dev_id;
+	uint32_t		cbd_immediate;
+};
+
+struct cb_devicenotifyargs {
+	int				 ndevs;
+	struct cb_devicenotifyitem	 *devs;
+};
+
+extern __be32 nfs4_callback_devicenotify(
+	struct cb_devicenotifyargs *args,
+	void *dummy, struct cb_process_state *cps);
+
 #endif /* CONFIG_NFS_V4_1 */
 extern int check_gss_callback_principal(struct nfs_client *, struct svc_rqst *);
 extern __be32 nfs4_callback_getattr(struct cb_getattrargs *args,
diff --git a/fs/nfs/callback_proc.c b/fs/nfs/callback_proc.c
index 2f41dccea18..d4d1954e9bb 100644
--- a/fs/nfs/callback_proc.c
+++ b/fs/nfs/callback_proc.c
@@ -139,7 +139,7 @@ static u32 initiate_file_draining(struct nfs_client *clp,
 	spin_lock(&ino->i_lock);
 	if (test_bit(NFS_LAYOUT_BULK_RECALL, &lo->plh_flags) ||
 	    mark_matching_lsegs_invalid(lo, &free_me_list,
-					args->cbl_range.iomode))
+					&args->cbl_range))
 		rv = NFS4ERR_DELAY;
 	else
 		rv = NFS4ERR_NOMATCHING_LAYOUT;
@@ -184,7 +184,7 @@ static u32 initiate_bulk_draining(struct nfs_client *clp,
 		ino = lo->plh_inode;
 		spin_lock(&ino->i_lock);
 		set_bit(NFS_LAYOUT_BULK_RECALL, &lo->plh_flags);
-		if (mark_matching_lsegs_invalid(lo, &free_me_list, range.iomode))
+		if (mark_matching_lsegs_invalid(lo, &free_me_list, &range))
 			rv = NFS4ERR_DELAY;
 		list_del_init(&lo->plh_bulk_recall);
 		spin_unlock(&ino->i_lock);
@@ -241,6 +241,53 @@ static void pnfs_recall_all_layouts(struct nfs_client *clp)
 	do_callback_layoutrecall(clp, &args);
 }
 
+__be32 nfs4_callback_devicenotify(struct cb_devicenotifyargs *args,
+				  void *dummy, struct cb_process_state *cps)
+{
+	int i;
+	__be32 res = 0;
+	struct nfs_client *clp = cps->clp;
+	struct nfs_server *server = NULL;
+
+	dprintk("%s: -->\n", __func__);
+
+	if (!clp) {
+		res = cpu_to_be32(NFS4ERR_OP_NOT_IN_SESSION);
+		goto out;
+	}
+
+	for (i = 0; i < args->ndevs; i++) {
+		struct cb_devicenotifyitem *dev = &args->devs[i];
+
+		if (!server ||
+		    server->pnfs_curr_ld->id != dev->cbd_layout_type) {
+			rcu_read_lock();
+			list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link)
+				if (server->pnfs_curr_ld &&
+				    server->pnfs_curr_ld->id == dev->cbd_layout_type) {
+					rcu_read_unlock();
+					goto found;
+				}
+			rcu_read_unlock();
+			dprintk("%s: layout type %u not found\n",
+				__func__, dev->cbd_layout_type);
+			continue;
+		}
+
+	found:
+		if (dev->cbd_notify_type == NOTIFY_DEVICEID4_CHANGE)
+			dprintk("%s: NOTIFY_DEVICEID4_CHANGE not supported, "
+				"deleting instead\n", __func__);
+		nfs4_delete_deviceid(server->pnfs_curr_ld, clp, &dev->cbd_dev_id);
+	}
+
+out:
+	kfree(args->devs);
+	dprintk("%s: exit with status = %u\n",
+		__func__, be32_to_cpu(res));
+	return res;
+}
+
 int nfs41_validate_delegation_stateid(struct nfs_delegation *delegation, const nfs4_stateid *stateid)
 {
 	if (delegation == NULL)
diff --git a/fs/nfs/callback_xdr.c b/fs/nfs/callback_xdr.c
index 00ecf62ce7c..c6c86a77e04 100644
--- a/fs/nfs/callback_xdr.c
+++ b/fs/nfs/callback_xdr.c
@@ -25,6 +25,7 @@
 
 #if defined(CONFIG_NFS_V4_1)
 #define CB_OP_LAYOUTRECALL_RES_MAXSZ	(CB_OP_HDR_RES_MAXSZ)
+#define CB_OP_DEVICENOTIFY_RES_MAXSZ	(CB_OP_HDR_RES_MAXSZ)
 #define CB_OP_SEQUENCE_RES_MAXSZ	(CB_OP_HDR_RES_MAXSZ + \
 					4 + 1 + 3)
 #define CB_OP_RECALLANY_RES_MAXSZ	(CB_OP_HDR_RES_MAXSZ)
@@ -284,6 +285,93 @@ out:
 	return status;
 }
 
+static
+__be32 decode_devicenotify_args(struct svc_rqst *rqstp,
+				struct xdr_stream *xdr,
+				struct cb_devicenotifyargs *args)
+{
+	__be32 *p;
+	__be32 status = 0;
+	u32 tmp;
+	int n, i;
+	args->ndevs = 0;
+
+	/* Num of device notifications */
+	p = read_buf(xdr, sizeof(uint32_t));
+	if (unlikely(p == NULL)) {
+		status = htonl(NFS4ERR_BADXDR);
+		goto out;
+	}
+	n = ntohl(*p++);
+	if (n <= 0)
+		goto out;
+
+	args->devs = kmalloc(n * sizeof(*args->devs), GFP_KERNEL);
+	if (!args->devs) {
+		status = htonl(NFS4ERR_DELAY);
+		goto out;
+	}
+
+	/* Decode each dev notification */
+	for (i = 0; i < n; i++) {
+		struct cb_devicenotifyitem *dev = &args->devs[i];
+
+		p = read_buf(xdr, (4 * sizeof(uint32_t)) + NFS4_DEVICEID4_SIZE);
+		if (unlikely(p == NULL)) {
+			status = htonl(NFS4ERR_BADXDR);
+			goto err;
+		}
+
+		tmp = ntohl(*p++);	/* bitmap size */
+		if (tmp != 1) {
+			status = htonl(NFS4ERR_INVAL);
+			goto err;
+		}
+		dev->cbd_notify_type = ntohl(*p++);
+		if (dev->cbd_notify_type != NOTIFY_DEVICEID4_CHANGE &&
+		    dev->cbd_notify_type != NOTIFY_DEVICEID4_DELETE) {
+			status = htonl(NFS4ERR_INVAL);
+			goto err;
+		}
+
+		tmp = ntohl(*p++);	/* opaque size */
+		if (((dev->cbd_notify_type == NOTIFY_DEVICEID4_CHANGE) &&
+		     (tmp != NFS4_DEVICEID4_SIZE + 8)) ||
+		    ((dev->cbd_notify_type == NOTIFY_DEVICEID4_DELETE) &&
+		     (tmp != NFS4_DEVICEID4_SIZE + 4))) {
+			status = htonl(NFS4ERR_INVAL);
+			goto err;
+		}
+		dev->cbd_layout_type = ntohl(*p++);
+		memcpy(dev->cbd_dev_id.data, p, NFS4_DEVICEID4_SIZE);
+		p += XDR_QUADLEN(NFS4_DEVICEID4_SIZE);
+
+		if (dev->cbd_layout_type == NOTIFY_DEVICEID4_CHANGE) {
+			p = read_buf(xdr, sizeof(uint32_t));
+			if (unlikely(p == NULL)) {
+				status = htonl(NFS4ERR_BADXDR);
+				goto err;
+			}
+			dev->cbd_immediate = ntohl(*p++);
+		} else {
+			dev->cbd_immediate = 0;
+		}
+
+		args->ndevs++;
+
+		dprintk("%s: type %d layout 0x%x immediate %d\n",
+			__func__, dev->cbd_notify_type, dev->cbd_layout_type,
+			dev->cbd_immediate);
+	}
+out:
+	dprintk("%s: status %d ndevs %d\n",
+		__func__, ntohl(status), args->ndevs);
+	return status;
+err:
+	kfree(args->devs);
+	goto out;
+}
+
 static __be32 decode_sessionid(struct xdr_stream *xdr,
 				 struct nfs4_sessionid *sid)
 {
@@ -639,10 +727,10 @@ preprocess_nfs41_op(int nop, unsigned int op_nr, struct callback_op **op)
 	case OP_CB_RECALL_ANY:
 	case OP_CB_RECALL_SLOT:
 	case OP_CB_LAYOUTRECALL:
+	case OP_CB_NOTIFY_DEVICEID:
 		*op = &callback_ops[op_nr];
 		break;
 
-	case OP_CB_NOTIFY_DEVICEID:
 	case OP_CB_NOTIFY:
 	case OP_CB_PUSH_DELEG:
 	case OP_CB_RECALLABLE_OBJ_AVAIL:
@@ -849,6 +937,12 @@ static struct callback_op callback_ops[] = {
 			(callback_decode_arg_t)decode_layoutrecall_args,
 		.res_maxsize = CB_OP_LAYOUTRECALL_RES_MAXSZ,
 	},
+	[OP_CB_NOTIFY_DEVICEID] = {
+		.process_op = (callback_process_op_t)nfs4_callback_devicenotify,
+		.decode_args =
+			(callback_decode_arg_t)decode_devicenotify_args,
+		.res_maxsize = CB_OP_DEVICENOTIFY_RES_MAXSZ,
+	},
 	[OP_CB_SEQUENCE] = {
 		.process_op = (callback_process_op_t)nfs4_callback_sequence,
 		.decode_args = (callback_decode_arg_t)decode_cb_sequence_args,
diff --git a/fs/nfs/client.c b/fs/nfs/client.c
index 139be9647d8..b3dc2b88b65 100644
--- a/fs/nfs/client.c
+++ b/fs/nfs/client.c
@@ -290,6 +290,8 @@ static void nfs_free_client(struct nfs_client *clp)
 	if (clp->cl_machine_cred != NULL)
 		put_rpccred(clp->cl_machine_cred);
 
+	nfs4_deviceid_purge_client(clp);
+
 	kfree(clp->cl_hostname);
 	kfree(clp);
 
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index 424e47773a8..ededdbd0db3 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -512,12 +512,7 @@ int nfs_readdir_page_filler(nfs_readdir_descriptor_t *desc, struct nfs_entry *en
 				struct page **xdr_pages, struct page *page, unsigned int buflen)
 {
 	struct xdr_stream stream;
-	struct xdr_buf buf = {
-		.pages = xdr_pages,
-		.page_len = buflen,
-		.buflen = buflen,
-		.len = buflen,
-	};
+	struct xdr_buf buf;
 	struct page *scratch;
 	struct nfs_cache_array *array;
 	unsigned int count = 0;
@@ -527,7 +522,7 @@ int nfs_readdir_page_filler(nfs_readdir_descriptor_t *desc, struct nfs_entry *en
 	if (scratch == NULL)
 		return -ENOMEM;
 
-	xdr_init_decode(&stream, &buf, NULL);
+	xdr_init_decode_pages(&stream, &buf, xdr_pages, buflen);
 	xdr_set_scratch_buffer(&stream, page_address(scratch), PAGE_SIZE);
 
 	do {
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index 873c6fa8bc3..144f2a3c718 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -1428,9 +1428,10 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
  */
 void nfs4_evict_inode(struct inode *inode)
 {
-	pnfs_destroy_layout(NFS_I(inode));
 	truncate_inode_pages(&inode->i_data, 0);
 	end_writeback(inode);
+	pnfs_return_layout(inode);
+	pnfs_destroy_layout(NFS_I(inode));
 	/* If we are holding a delegation, return it! */
 	nfs_inode_return_delegation_noreclaim(inode);
 	/* First call standard NFS clear_inode() code */
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index 2df6ca7b589..b9056cbe68d 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -310,6 +310,7 @@ extern int nfs_migrate_page(struct address_space *,
 #endif
 
 /* nfs4proc.c */
+extern void __nfs4_read_done_cb(struct nfs_read_data *);
 extern void nfs4_reset_read(struct rpc_task *task, struct nfs_read_data *data);
 extern int nfs4_init_client(struct nfs_client *clp,
 			    const struct rpc_timeout *timeparms,
diff --git a/fs/nfs/nfs4filelayout.c b/fs/nfs/nfs4filelayout.c
index be79dc9f386..426908809c9 100644
--- a/fs/nfs/nfs4filelayout.c
+++ b/fs/nfs/nfs4filelayout.c
@@ -421,6 +421,7 @@ filelayout_check_layout(struct pnfs_layout_hdr *lo,
 			struct nfs4_deviceid *id,
 			gfp_t gfp_flags)
 {
+	struct nfs4_deviceid_node *d;
 	struct nfs4_file_layout_dsaddr *dsaddr;
 	int status = -EINVAL;
 	struct nfs_server *nfss = NFS_SERVER(lo->plh_inode);
@@ -428,7 +429,7 @@ filelayout_check_layout(struct pnfs_layout_hdr *lo,
 	dprintk("--> %s\n", __func__);
 
 	if (fl->pattern_offset > lgr->range.offset) {
-		dprintk("%s pattern_offset %lld to large\n",
+		dprintk("%s pattern_offset %lld too large\n",
 				__func__, fl->pattern_offset);
 		goto out;
 	}
@@ -440,12 +441,14 @@ filelayout_check_layout(struct pnfs_layout_hdr *lo,
 	}
 
 	/* find and reference the deviceid */
-	dsaddr = nfs4_fl_find_get_deviceid(id);
-	if (dsaddr == NULL) {
+	d = nfs4_find_get_deviceid(NFS_SERVER(lo->plh_inode)->pnfs_curr_ld,
+				   NFS_SERVER(lo->plh_inode)->nfs_client, id);
+	if (d == NULL) {
 		dsaddr = get_device_info(lo->plh_inode, id, gfp_flags);
 		if (dsaddr == NULL)
 			goto out;
-	}
+	} else
+		dsaddr = container_of(d, struct nfs4_file_layout_dsaddr, id_node);
 	fl->dsaddr = dsaddr;
 
 	if (fl->first_stripe_index < 0 ||
@@ -507,12 +510,7 @@ filelayout_decode_layout(struct pnfs_layout_hdr *flo,
 			 gfp_t gfp_flags)
 {
 	struct xdr_stream stream;
-	struct xdr_buf buf = {
-		.pages =  lgr->layoutp->pages,
-		.page_len =  lgr->layoutp->len,
-		.buflen =  lgr->layoutp->len,
-		.len = lgr->layoutp->len,
-	};
+	struct xdr_buf buf;
 	struct page *scratch;
 	__be32 *p;
 	uint32_t nfl_util;
@@ -524,7 +522,7 @@ filelayout_decode_layout(struct pnfs_layout_hdr *flo,
 	if (!scratch)
 		return -ENOMEM;
 
-	xdr_init_decode(&stream, &buf, NULL);
+	xdr_init_decode_pages(&stream, &buf, lgr->layoutp->pages, lgr->layoutp->len);
 	xdr_set_scratch_buffer(&stream, page_address(scratch), PAGE_SIZE);
 
 	/* 20 = ufl_util (4), first_stripe_index (4), pattern_offset (8),
@@ -535,7 +533,7 @@ filelayout_decode_layout(struct pnfs_layout_hdr *flo,
 
 	memcpy(id, p, sizeof(*id));
 	p += XDR_QUADLEN(NFS4_DEVICEID4_SIZE);
-	print_deviceid(id);
+	nfs4_print_deviceid(id);
 
 	nfl_util = be32_to_cpup(p++);
 	if (nfl_util & NFL4_UFLG_COMMIT_THRU_MDS)
@@ -653,16 +651,19 @@ filelayout_alloc_lseg(struct pnfs_layout_hdr *layoutid,
 /*
  * filelayout_pg_test(). Called by nfs_can_coalesce_requests()
  *
- * return 1 :  coalesce page
- * return 0 :  don't coalesce page
+ * return true  : coalesce page
+ * return false : don't coalesce page
  */
-int
+bool
 filelayout_pg_test(struct nfs_pageio_descriptor *pgio, struct nfs_page *prev,
 		   struct nfs_page *req)
 {
 	u64 p_stripe, r_stripe;
 	u32 stripe_unit;
 
+	if (!pnfs_generic_pg_test(pgio, prev, req))
+		return 0;
+
 	if (!pgio->pg_lseg)
 		return 1;
 	p_stripe = (u64)prev->wb_index << PAGE_CACHE_SHIFT;
@@ -860,6 +861,12 @@ filelayout_commit_pagelist(struct inode *inode, struct list_head *mds_pages,
 	return -ENOMEM;
 }
 
+static void
+filelayout_free_deveiceid_node(struct nfs4_deviceid_node *d)
+{
+	nfs4_fl_free_deviceid(container_of(d, struct nfs4_file_layout_dsaddr, id_node));
+}
+
 static struct pnfs_layoutdriver_type filelayout_type = {
 	.id			= LAYOUT_NFSV4_1_FILES,
 	.name			= "LAYOUT_NFSV4_1_FILES",
@@ -872,6 +879,7 @@ static struct pnfs_layoutdriver_type filelayout_type = {
 	.commit_pagelist	= filelayout_commit_pagelist,
 	.read_pagelist		= filelayout_read_pagelist,
 	.write_pagelist		= filelayout_write_pagelist,
+	.free_deviceid_node	= filelayout_free_deveiceid_node,
 };
 
 static int __init nfs4filelayout_init(void)
diff --git a/fs/nfs/nfs4filelayout.h b/fs/nfs/nfs4filelayout.h
index 2b461d77b43..cebe01e3795 100644
--- a/fs/nfs/nfs4filelayout.h
+++ b/fs/nfs/nfs4filelayout.h
@@ -59,9 +59,7 @@ struct nfs4_pnfs_ds {
 #define NFS4_DEVICE_ID_NEG_ENTRY	0x00000001
 
 struct nfs4_file_layout_dsaddr {
-	struct hlist_node		node;
-	struct nfs4_deviceid		deviceid;
-	atomic_t			ref;
+	struct nfs4_deviceid_node	id_node;
 	unsigned long			flags;
 	u32				stripe_count;
 	u8				*stripe_indices;
@@ -95,14 +93,12 @@ extern struct nfs_fh *
 nfs4_fl_select_ds_fh(struct pnfs_layout_segment *lseg, u32 j);
 
 extern void print_ds(struct nfs4_pnfs_ds *ds);
-extern void print_deviceid(struct nfs4_deviceid *dev_id);
 u32 nfs4_fl_calc_j_index(struct pnfs_layout_segment *lseg, loff_t offset);
 u32 nfs4_fl_calc_ds_index(struct pnfs_layout_segment *lseg, u32 j);
 struct nfs4_pnfs_ds *nfs4_fl_prepare_ds(struct pnfs_layout_segment *lseg,
 					u32 ds_idx);
-extern struct nfs4_file_layout_dsaddr *
-nfs4_fl_find_get_deviceid(struct nfs4_deviceid *dev_id);
 extern void nfs4_fl_put_deviceid(struct nfs4_file_layout_dsaddr *dsaddr);
+extern void nfs4_fl_free_deviceid(struct nfs4_file_layout_dsaddr *dsaddr);
 struct nfs4_file_layout_dsaddr *
 get_device_info(struct inode *inode, struct nfs4_deviceid *dev_id, gfp_t gfp_flags);
 
diff --git a/fs/nfs/nfs4filelayoutdev.c b/fs/nfs/nfs4filelayoutdev.c
index db07c7af139..3b7bf137726 100644
--- a/fs/nfs/nfs4filelayoutdev.c
+++ b/fs/nfs/nfs4filelayoutdev.c
@@ -37,30 +37,6 @@
 #define NFSDBG_FACILITY		NFSDBG_PNFS_LD
 
 /*
- * Device ID RCU cache. A device ID is unique per client ID and layout type.
- */
-#define NFS4_FL_DEVICE_ID_HASH_BITS	5
-#define NFS4_FL_DEVICE_ID_HASH_SIZE	(1 << NFS4_FL_DEVICE_ID_HASH_BITS)
-#define NFS4_FL_DEVICE_ID_HASH_MASK	(NFS4_FL_DEVICE_ID_HASH_SIZE - 1)
-
-static inline u32
-nfs4_fl_deviceid_hash(struct nfs4_deviceid *id)
-{
-	unsigned char *cptr = (unsigned char *)id->data;
-	unsigned int nbytes = NFS4_DEVICEID4_SIZE;
-	u32 x = 0;
-
-	while (nbytes--) {
-		x *= 37;
-		x += *cptr++;
-	}
-	return x & NFS4_FL_DEVICE_ID_HASH_MASK;
-}
-
-static struct hlist_head filelayout_deviceid_cache[NFS4_FL_DEVICE_ID_HASH_SIZE];
-static DEFINE_SPINLOCK(filelayout_deviceid_lock);
-
-/*
  * Data server cache
  *
  * Data servers can be mapped to different device ids.
@@ -89,27 +65,6 @@ print_ds(struct nfs4_pnfs_ds *ds)
 		ds->ds_clp ? ds->ds_clp->cl_exchange_flags : 0);
 }
 
-void
-print_ds_list(struct nfs4_file_layout_dsaddr *dsaddr)
-{
-	int i;
-
-	ifdebug(FACILITY) {
-		printk("%s dsaddr->ds_num %d\n", __func__,
-		       dsaddr->ds_num);
-		for (i = 0; i < dsaddr->ds_num; i++)
-			print_ds(dsaddr->ds_list[i]);
-	}
-}
-
-void print_deviceid(struct nfs4_deviceid *id)
-{
-	u32 *p = (u32 *)id;
-
-	dprintk("%s: device id= [%x%x%x%x]\n", __func__,
-		p[0], p[1], p[2], p[3]);
-}
-
 /* nfs4_ds_cache_lock is held */
 static struct nfs4_pnfs_ds *
 _data_server_lookup_locked(u32 ip_addr, u32 port)
@@ -201,13 +156,13 @@ destroy_ds(struct nfs4_pnfs_ds *ds)
 	kfree(ds);
 }
 
-static void
+void
 nfs4_fl_free_deviceid(struct nfs4_file_layout_dsaddr *dsaddr)
 {
 	struct nfs4_pnfs_ds *ds;
 	int i;
 
-	print_deviceid(&dsaddr->deviceid);
+	nfs4_print_deviceid(&dsaddr->id_node.deviceid);
 
 	for (i = 0; i < dsaddr->ds_num; i++) {
 		ds = dsaddr->ds_list[i];
@@ -353,12 +308,7 @@ decode_device(struct inode *ino, struct pnfs_device *pdev, gfp_t gfp_flags)
 	u8 max_stripe_index;
 	struct nfs4_file_layout_dsaddr *dsaddr = NULL;
 	struct xdr_stream stream;
-	struct xdr_buf buf = {
-		.pages = pdev->pages,
-		.page_len = pdev->pglen,
-		.buflen = pdev->pglen,
-		.len = pdev->pglen,
-	};
+	struct xdr_buf buf;
 	struct page *scratch;
 
 	/* set up xdr stream */
@@ -366,7 +316,7 @@ decode_device(struct inode *ino, struct pnfs_device *pdev, gfp_t gfp_flags)
 	if (!scratch)
 		goto out_err;
 
-	xdr_init_decode(&stream, &buf, NULL);
+	xdr_init_decode_pages(&stream, &buf, pdev->pages, pdev->pglen);
 	xdr_set_scratch_buffer(&stream, page_address(scratch), PAGE_SIZE);
 
 	/* Get the stripe count (number of stripe index) */
@@ -431,8 +381,10 @@ decode_device(struct inode *ino, struct pnfs_device *pdev, gfp_t gfp_flags)
 	dsaddr->stripe_indices = stripe_indices;
 	stripe_indices = NULL;
 	dsaddr->ds_num = num;
-
-	memcpy(&dsaddr->deviceid, &pdev->dev_id, sizeof(pdev->dev_id));
+	nfs4_init_deviceid_node(&dsaddr->id_node,
+				NFS_SERVER(ino)->pnfs_curr_ld,
+				NFS_SERVER(ino)->nfs_client,
+				&pdev->dev_id);
 
 	for (i = 0; i < dsaddr->ds_num; i++) {
 		int j;
@@ -505,8 +457,8 @@ out_err:
 static struct nfs4_file_layout_dsaddr *
 decode_and_add_device(struct inode *inode, struct pnfs_device *dev, gfp_t gfp_flags)
 {
-	struct nfs4_file_layout_dsaddr *d, *new;
-	long hash;
+	struct nfs4_deviceid_node *d;
+	struct nfs4_file_layout_dsaddr *n, *new;
 
 	new = decode_device(inode, dev, gfp_flags);
 	if (!new) {
@@ -515,20 +467,13 @@ decode_and_add_device(struct inode *inode, struct pnfs_device *dev, gfp_t gfp_fl
 		return NULL;
 	}
 
-	spin_lock(&filelayout_deviceid_lock);
-	d = nfs4_fl_find_get_deviceid(&new->deviceid);
-	if (d) {
-		spin_unlock(&filelayout_deviceid_lock);
+	d = nfs4_insert_deviceid_node(&new->id_node);
+	n = container_of(d, struct nfs4_file_layout_dsaddr, id_node);
+	if (n != new) {
 		nfs4_fl_free_deviceid(new);
-		return d;
+		return n;
 	}
 
-	INIT_HLIST_NODE(&new->node);
-	atomic_set(&new->ref, 1);
-	hash = nfs4_fl_deviceid_hash(&new->deviceid);
-	hlist_add_head_rcu(&new->node, &filelayout_deviceid_cache[hash]);
-	spin_unlock(&filelayout_deviceid_lock);
-
 	return new;
 }
 
@@ -600,35 +545,7 @@ out_free:
 void
 nfs4_fl_put_deviceid(struct nfs4_file_layout_dsaddr *dsaddr)
 {
-	if (atomic_dec_and_lock(&dsaddr->ref, &filelayout_deviceid_lock)) {
-		hlist_del_rcu(&dsaddr->node);
-		spin_unlock(&filelayout_deviceid_lock);
-
-		synchronize_rcu();
-		nfs4_fl_free_deviceid(dsaddr);
-	}
-}
-
-struct nfs4_file_layout_dsaddr *
-nfs4_fl_find_get_deviceid(struct nfs4_deviceid *id)
-{
-	struct nfs4_file_layout_dsaddr *d;
-	struct hlist_node *n;
-	long hash = nfs4_fl_deviceid_hash(id);
-
-
-	rcu_read_lock();
-	hlist_for_each_entry_rcu(d, n, &filelayout_deviceid_cache[hash], node) {
-		if (!memcmp(&d->deviceid, id, sizeof(*id))) {
-			if (!atomic_inc_not_zero(&d->ref))
-				goto fail;
-			rcu_read_unlock();
-			return d;
-		}
-	}
-fail:
-	rcu_read_unlock();
-	return NULL;
+	nfs4_put_deviceid_node(&dsaddr->id_node);
 }
 
 /*
@@ -676,15 +593,15 @@ static void
 filelayout_mark_devid_negative(struct nfs4_file_layout_dsaddr *dsaddr,
 			       int err, u32 ds_addr)
 {
-	u32 *p = (u32 *)&dsaddr->deviceid;
+	u32 *p = (u32 *)&dsaddr->id_node.deviceid;
 
 	printk(KERN_ERR "NFS: data server %x connection error %d."
 		" Deviceid [%x%x%x%x] marked out of use.\n",
 		ds_addr, err, p[0], p[1], p[2], p[3]);
 
-	spin_lock(&filelayout_deviceid_lock);
+	spin_lock(&nfs4_ds_cache_lock);
 	dsaddr->flags |= NFS4_DEVICE_ID_NEG_ENTRY;
-	spin_unlock(&filelayout_deviceid_lock);
+	spin_unlock(&nfs4_ds_cache_lock);
 }
 
 struct nfs4_pnfs_ds *
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index d0e15dba7a5..d2c4b59c896 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -2363,6 +2363,9 @@ nfs4_proc_setattr(struct dentry *dentry, struct nfs_fattr *fattr,
 	struct nfs4_state *state = NULL;
 	int status;
 
+	if (pnfs_ld_layoutret_on_setattr(inode))
+		pnfs_return_layout(inode);
+
 	nfs_fattr_init(fattr);
 	
 	/* Search for an existing open(O_WRITE) file */
@@ -3177,6 +3180,11 @@ static int nfs4_proc_pathconf(struct nfs_server *server, struct nfs_fh *fhandle,
 	return err;
 }
 
+void __nfs4_read_done_cb(struct nfs_read_data *data)
+{
+	nfs_invalidate_atime(data->inode);
+}
+
 static int nfs4_read_done_cb(struct rpc_task *task, struct nfs_read_data *data)
 {
 	struct nfs_server *server = NFS_SERVER(data->inode);
@@ -3186,7 +3194,7 @@ static int nfs4_read_done_cb(struct rpc_task *task, struct nfs_read_data *data)
 		return -EAGAIN;
 	}
 
-	nfs_invalidate_atime(data->inode);
+	__nfs4_read_done_cb(data);
 	if (task->tk_status > 0)
 		renew_lease(server, data->timestamp);
 	return 0;
@@ -3200,7 +3208,8 @@ static int nfs4_read_done(struct rpc_task *task, struct nfs_read_data *data)
 	if (!nfs4_sequence_done(task, &data->res.seq_res))
 		return -EAGAIN;
 
-	return data->read_done_cb(task, data);
+	return data->read_done_cb ? data->read_done_cb(task, data) :
+				    nfs4_read_done_cb(task, data);
 }
 
 static void nfs4_proc_read_setup(struct nfs_read_data *data, struct rpc_message *msg)
@@ -3245,7 +3254,8 @@ static int nfs4_write_done(struct rpc_task *task, struct nfs_write_data *data)
 {
 	if (!nfs4_sequence_done(task, &data->res.seq_res))
 		return -EAGAIN;
-	return data->write_done_cb(task, data);
+	return data->write_done_cb ? data->write_done_cb(task, data) :
+		nfs4_write_done_cb(task, data);
 }
 
 /* Reset the the nfs_write_data to send the write to the MDS. */
@@ -5671,6 +5681,88 @@ int nfs4_proc_layoutget(struct nfs4_layoutget *lgp)
 	return status;
 }
 
+static void
+nfs4_layoutreturn_prepare(struct rpc_task *task, void *calldata)
+{
+	struct nfs4_layoutreturn *lrp = calldata;
+
+	dprintk("--> %s\n", __func__);
+	if (nfs41_setup_sequence(lrp->clp->cl_session, &lrp->args.seq_args,
+				&lrp->res.seq_res, 0, task))
+		return;
+	rpc_call_start(task);
+}
+
+static void nfs4_layoutreturn_done(struct rpc_task *task, void *calldata)
+{
+	struct nfs4_layoutreturn *lrp = calldata;
+	struct nfs_server *server;
+
+	dprintk("--> %s\n", __func__);
+
+	if (!nfs4_sequence_done(task, &lrp->res.seq_res))
+		return;
+
+	server = NFS_SERVER(lrp->args.inode);
+	if (nfs4_async_handle_error(task, server, NULL) == -EAGAIN) {
+		nfs_restart_rpc(task, lrp->clp);
+		return;
+	}
+	if (task->tk_status == 0) {
+		struct pnfs_layout_hdr *lo = NFS_I(lrp->args.inode)->layout;
+
+		if (lrp->res.lrs_present) {
+			spin_lock(&lo->plh_inode->i_lock);
+			pnfs_set_layout_stateid(lo, &lrp->res.stateid, true);
+			spin_unlock(&lo->plh_inode->i_lock);
+		} else
+			BUG_ON(!list_empty(&lo->plh_segs));
+	}
+	dprintk("<-- %s\n", __func__);
+}
+
+static void nfs4_layoutreturn_release(void *calldata)
+{
+	struct nfs4_layoutreturn *lrp = calldata;
+
+	dprintk("--> %s\n", __func__);
+	put_layout_hdr(NFS_I(lrp->args.inode)->layout);
+	kfree(calldata);
+	dprintk("<-- %s\n", __func__);
+}
+
+static const struct rpc_call_ops nfs4_layoutreturn_call_ops = {
+	.rpc_call_prepare = nfs4_layoutreturn_prepare,
+	.rpc_call_done = nfs4_layoutreturn_done,
+	.rpc_release = nfs4_layoutreturn_release,
+};
+
+int nfs4_proc_layoutreturn(struct nfs4_layoutreturn *lrp)
+{
+	struct rpc_task *task;
+	struct rpc_message msg = {
+		.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_LAYOUTRETURN],
+		.rpc_argp = &lrp->args,
+		.rpc_resp = &lrp->res,
+	};
+	struct rpc_task_setup task_setup_data = {
+		.rpc_client = lrp->clp->cl_rpcclient,
+		.rpc_message = &msg,
+		.callback_ops = &nfs4_layoutreturn_call_ops,
+		.callback_data = lrp,
+	};
+	int status;
+
+	dprintk("--> %s\n", __func__);
+	task = rpc_run_task(&task_setup_data);
+	if (IS_ERR(task))
+		return PTR_ERR(task);
+	status = task->tk_status;
+	dprintk("<-- %s status=%d\n", __func__, status);
+	rpc_put_task(task);
+	return status;
+}
+
 static int
 _nfs4_proc_getdeviceinfo(struct nfs_server *server, struct pnfs_device *pdev)
 {
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index c3ccd2c4683..d869a5e5464 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -338,7 +338,11 @@ static int nfs4_stat_to_errno(int);
 				1 /* layoutupdate4 layout type */ + \
 				1 /* NULL filelayout layoutupdate4 payload */)
 #define decode_layoutcommit_maxsz (op_decode_hdr_maxsz + 3)
-
+#define encode_layoutreturn_maxsz (8 + op_encode_hdr_maxsz + \
+				encode_stateid_maxsz + \
+				1 /*